My background is in python, but I am relatively new to numpy, so please bear with me if I make any mistakes.
Currently, I am working on reading a .wav file that contains multiple frequencies separated by periods of silence. Up until now, I have been successful in extracting the values and identifying the sections within the file where there is sound. My next goal is to apply Discrete Cosine Transform to calculate the frequencies from these segments (reference: how to extract frequency associated with fft values in python)
However, I encountered an error:
index 46392 is out of bounds for axis 0 with size 25
This is the code snippet where the error occurs:
import wave
import struct
import numpy as np
def isSilence(windowPosition):
sumVal = sum([x*x for x in sound[windowPosition:windowPosition+windowSize+1]])
avg = sumVal / windowSize
if avg <= 0.0001:
return True
else:
return False
# Read from the wav file
sound_file = wave.open('test.wav', 'r')
file_length = sound_file.getnframes()
data = sound_file.readframes(file_length)
sound_file.close()
data = struct.unpack('{n}h'.format(n=file_length), data)
sound = np.array(data)
i = 0
windowSize = 2205
windowPosition = 0
listOfLists = []
listOfLists.append([])
maxVal = len(sound) - windowSize
while True:
if windowPosition >= maxVal:
break
if not isSilence(windowPosition):
while not isSilence(windowPosition):
listOfLists[i].append(sound[windowPosition:windowPosition + windowSize + 1])
windowPosition += windowSize
listOfLists.append([])
i += 1
windowPosition += windowSize
frequencies = []
for signal in listOfLists:
if not signal:
break
w = np.fft.fft(signal)
freqs = np.fft.fftfreq(len(w))
l = len(signal)
imax = np.argmax(np.abs(w))
fs = freqs[imax]
freq = imax * fs / l
frequencies.append(freq)
print(frequencies)
In addition, here is the traceback message:
Traceback (most recent call last):
File "final.py", line 61, in <module>
fs = freqs[imax]
IndexError: index 46392 is out of bounds for axis 0 with size 21